figure

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research data and conceptual descriptions to generate Python code and Mermaid diagrams.
  • Ingestion points: Data and figure descriptions provided in user prompts processed via the Figure Generator instructions in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters to separate user data from internal instructions for the agent.
  • Capability inventory: The skill provides commands for the agent to install dependencies and execute syntax validation on generated code.
  • Sanitization: No validation or sanitization is performed on user data before it is interpolated into the generated scripts or diagrams.
  • [COMMAND_EXECUTION]: The skill includes shell instructions for validating the syntax of generated Python scripts.
  • Evidence: python -c "import ast; ast.parse(open('figure1.py').read()); print('✅ Syntax OK')" found in SKILL.md. While this uses the AST module for parsing without execution, it represents a command execution surface.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install external Python packages to run the generated visualizations.
  • Evidence: pip install matplotlib seaborn numpy in SKILL.md. These are well-known, official libraries from the Python Package Index (PyPI) used for data visualization.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:32 AM